{"id":"W4378419649","doi":"10.1007/978-3-031-33380-4_31","title":"RLMixer: A Reinforcement Learning Approach for Integrated Ranking with Contrastive User Preference Modeling","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Ranking (information retrieval); Computer science; Reinforcement learning; Preference; Recommender system; Metric (unit); Artificial intelligence; Revenue; Machine learning; Preference learning; Term (time); Information retrieval","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003009116,0.001098278,0.002043289,0.0007258281,0.0005010121,0.001242814,0.003444027,0.001384182,0.007595565],"category_scores_gemma":[0.005854438,0.0008495115,0.001088899,0.0009633807,0.0004985387,0.001978917,0.00215256,0.002927215,0.00268874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008462141,"about_ca_system_score_gemma":0.001173477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006877244,"about_ca_topic_score_gemma":0.0119361,"domain_scores_codex":[0.9984768,0.0006737285,0.00006625154,0.000291955,0.0003872443,0.000104019],"domain_scores_gemma":[0.9978647,0.001212001,0.0001139223,0.000340807,0.0003531578,0.0001154199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004670645,0.0006748376,0.001067088,0.0002309514,0.0003502351,0.0001036155,0.0001663178,0.3903199,0.006766765,0.02037448,0.01212486,0.5673538],"study_design_scores_gemma":[0.00001711891,0.00003093502,0.00005091939,0.000003651927,0.000009967816,0.000009812821,0.000003332416,0.9957249,0.0006905147,0.002683258,0.0007679941,0.000007504432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002048837,0.0000819065,0.9954528,0.00004498605,0.00003146633,0.00005770574,0.00006242502,0.001680732,0.0005391197],"genre_scores_gemma":[0.1076861,0.0001222157,0.8856477,0.0001837842,0.00007677618,0.0002857997,0.0002957064,0.0004799496,0.005222003],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007595565,"threshold_uncertainty_score":0.0254097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0475176102982988,"score_gpt":0.2490568989841326,"score_spread":0.2015392886858338,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}